CN110062112A - Data processing method, device, equipment and computer readable storage medium - Google Patents
Data processing method, device, equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN110062112A CN110062112A CN201910199189.4A CN201910199189A CN110062112A CN 110062112 A CN110062112 A CN 110062112A CN 201910199189 A CN201910199189 A CN 201910199189A CN 110062112 A CN110062112 A CN 110062112A
- Authority
- CN
- China
- Prior art keywords
- data
- message registration
- data processing
- destination call
- processing method
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2455—Query execution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/254—Extract, transform and load [ETL] procedures, e.g. ETL data flows in data warehouses
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/22—Arrangements for supervision, monitoring or testing
- H04M3/2218—Call detail recording
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/22—Arrangements for supervision, monitoring or testing
- H04M3/36—Statistical metering, e.g. recording occasions when traffic exceeds capacity of trunks
- H04M3/367—Traffic or load control
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/42136—Administration or customisation of services
- H04M3/4217—Managing service interactions
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/42221—Conversation recording systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
- H04M3/51—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
- H04M3/5141—Details of processing calls and other types of contacts in an unified manner
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Marketing (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention belongs to field of data storage, a kind of data processing method, device, equipment and computer readable storage medium are provided, this method comprises: receiving the message registration data that call center generates, and the message registration data are sent to message queue;It from the message queue, extracts that the message registration data are corresponding by duration, and from the message registration data for determining that the duration of call is located within the scope of preset duration in the message registration data, records data as destination call;Destination call record data are stored into key value database.The present invention can reduce operation system load, improve the intelligence and convenience of storage message registration data, and can reduce the limitation of message registration data storage.
Description
Technical field
The present invention relates to field of data storage more particularly to a kind of data processing method, device, equipment and computer-readable
Storage medium.
Background technique
For enterprise, phone activity is related to the business such as client's consulting, product promotion, client's return visit, satisfaction investigation, is
The important ring that enterprise commences business.And being growing with scope of the enterprise, ten hundreds of phone activities need to be carried out daily,
Call center can constantly generate the message registration data of magnanimity in real time, be by operation system in set time point at this stage
(such as morning) carries out the processing such as offline excavation, storage to message registration data, however, due to operation system resource constraint,
This mode has been difficult to cope with magnanimity message registration data that are real-time and persistently generating.
Summary of the invention
The main purpose of the present invention is to provide a kind of data processing method, device, equipment and computer-readable storage mediums
Matter, it is intended to solve operation system and be difficult to cope with call center to ask with the technology of magnanimity message registration data that persistently generates in real time
Topic.
To achieve the above object, the present invention provides a kind of data processing method, and the data processing method is applied to data
Processing system, the data processing system include receiving module, message queue, processing module and key value database, the data
Processing method the following steps are included:
The message registration data that call center generates are received, and the message registration data are sent to message queue;
From the message queue, it is corresponding by duration to extract the message registration data, and remember from the call
The message registration data that the duration of call is located within the scope of preset duration are determined in record data, record number as destination call
According to;
Destination call record data are stored into key value database.
Optionally, described that destination call record data are stored the step into key value database and include:
Corresponding telephone number is extracted from destination call record data;
Using the telephone number of extraction as key, the sorting position of the key is set;
Corresponding destination call record data are stored to the key value database according to the sorting position of the key of setting
In.
Optionally, it is described destination call record data are stored into the step into key value database after, comprising:
When detecting message registration data inquiry request, telephone number and to be checked is extracted from the inquiry request
Beginning and ending time;
Using the telephone number and the beginning and ending time as querying condition, inquired in the key value database corresponding
Message registration data and feedback query result.
Optionally, it is described destination call record data are stored into the step into key value database after, further includes:
When detecting that the time of push product reaches, it is default for obtaining from the key value database apart from current time
Destination call in duration records data;
The destination call record data of acquisition are analyzed, determine target customer;
The customer information of the target customer is obtained from operation system;
Determine the recommended products of the target customer according to the customer information, and by the Push Service module to institute
It states target customer and pushes the recommended products.
Optionally, destination call record data the step of analyzing, determining target customer of described pair of acquisition, includes:
Calling record is extracted from the destination call of acquisition record data;
Identify determine whether the calling record extracted includes to be related to product purchase intention to the calling record of extraction
Keyword;
For the calling record of the keyword comprising being related to product purchase intention, corresponding destination call is recorded in data
Contact person be determined as target customer.
Optionally, the recommended products step that the target customer is determined according to the customer information includes:
The customer information is input in trained neural network model and is analyzed, the neural network mould is obtained
The feature tag of the target customer of type output;
The recommended products of the target customer is determined according to the feature tag.
Optionally, the step of recommended products that the target customer is determined according to the feature tag includes:
The feature tag is analyzed, determines characterizing population group belonging to the target customer;
Inquiry and the matched product of the characterizing population group from the product library of operation system, the product are determined as described
The recommended products of target customer.
In addition, to achieve the above object, the present invention also provides data processing equipment, the data processing equipment includes:
Receiving module is sent for receiving the message registration data of call center's generation, and by the message registration data
To message queue;
Determining module, it is corresponding by duration for from the message queue, extracting the message registration data, and
From the message registration data for determining that the duration of call is located within the scope of preset duration in the message registration data, as mesh
Mark message registration data;
Memory module, for storing destination call record data into key value database.
In addition, to achieve the above object, the present invention also provides a kind of data processing equipment, the data processing equipment includes
Processor, memory and it is stored in the data processor that can be executed on the memory and by the processor, wherein institute
When stating data processor and being executed by the processor, realize such as the step of above-mentioned data processing method.
In addition, to achieve the above object, it is described computer-readable the present invention also provides a kind of computer readable storage medium
Data processor is stored on storage medium, wherein realizing when the data processor is executed by processor as above-mentioned
The step of data processing method.
The present invention provides a kind of data processing method, first the message registration data of reception call center generation, and will lead to
Words record data are sent to message queue, then from the message queue, extract that the message registration data are corresponding to be passed through
Duration, and determine that destination call records data from message registration data according to the duration of call of extraction, and then by destination call
Record data are stored into key value database.The present invention utilizes stream data processing technique, remembers to the call that call center generates
Record data are excavated and are stored, more convenient and intelligent, and will not occupy operation system resource, alleviate the negative of operation system
It carries, while reducing the degree of coupling between call center and operation system, in addition, saving message registration number by key value database
According to the key value database can extend, and memory capacity will not be limited, and reduce the limitation of message registration data storage.
Detailed description of the invention
Fig. 1 is the hardware structural diagram of data processing equipment involved in the embodiment of the present invention;
Fig. 2 is the flow diagram of data processing method first embodiment of the present invention;
Fig. 3 is the flow diagram of data processing method second embodiment of the present invention;
Fig. 4 is the functional block diagram of data processing equipment first embodiment of the present invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
The present embodiments relate to data processing method be mainly used in data processing equipment, which can
To be the equipment having data processing function such as personal computer (personal computer, PC), server.
Referring to Fig.1, Fig. 1 is the hardware structural diagram of data processing equipment involved in the embodiment of the present invention.This
In inventive embodiments, data processing equipment may include (such as the central processing unit Central Processing of processor 1001
Unit, CPU), communication bus 1002, user interface 1003, network interface 1004, memory 1005.Wherein, communication bus 1002
For realizing the connection communication between these components;User interface 1003 may include display screen (Display), input unit ratio
Such as keyboard (Keyboard);Network interface 1004 optionally may include standard wireline interface and wireless interface (such as Wireless Fidelity
WIreless-FIdelity, WI-FI interface);Memory 1005 can be high-speed random access memory (random access
Memory, RAM), it is also possible to stable memory (non-volatile memory), such as magnetic disk storage, memory
1005 optionally can also be the storage device independently of aforementioned processor 1001.It will be understood by those skilled in the art that in Fig. 1
The hardware configuration that shows does not constitute a limitation of the invention simultaneously, may include than illustrating more or fewer components, or combination
Certain components or different component layouts.
With continued reference to Fig. 1, the memory 1005 in Fig. 1 as a kind of computer storage medium may include operating system,
Network communication module and data processor.In Fig. 1, reason device 1001 can be called at the data stored in memory 1005
Program is managed, and the data processing method of various embodiments of the present invention offer is provided.
The embodiment of the invention provides a kind of data processing methods.
It is the flow diagram of data processing method first embodiment of the present invention referring to Fig. 2, Fig. 2.
In the present embodiment, the data processing method the following steps are included:
Step S10 receives the message registration data that call center generates, and the message registration data is sent to message
Queue;
Step S20, from the message queue, it is corresponding by duration to extract the message registration data, and from institute
The message registration data for determining that the duration of call is located within the scope of preset duration in message registration data are stated, it is logical as target
Words record data;
Step S30 stores destination call record data into key value database.
The data processing method of the present embodiment is used to handle the magnanimity message registration number that call center is real-time and persistently generates
According to belonging to stream data.In the present embodiment, it is in advance based on stream data processing frame and builds data processing system, it can be with
The stream data processing frame of exploitation and operation data processing system on the stream data processing frame of open source, open source can be
Hadoop (stream data processing architecture), Storm, Flink etc..The present embodiment data processing system include receiving module,
Message queue (Message queue), processing module and key assignments (Key-Value) database.Wherein, message queue is in message
Transmission process in save message container;Key value database is non-relational database, for the storage of ultra-large data,
It is read and write, is deleted etc. to the corresponding data record of Key (i.e. Value) and operated using key (Key) as index, due to key
Value Data library is only concerned the process by Key index Value, is indifferent to the structure and content of the specific data stored in Value,
Therefore for key value database is compared to relevant database, there is function-specific, planarization to access data performance high, distributed
The strong feature of the scalability of processing.Data processing system is interconnected with call center and operation system respectively.
The data processing method of the present embodiment is realized by data processing system.The present embodiment is right by data processing system
The message registration data that call center generates are handled, and operation system resource will not be occupied, and can mitigate the negative of operation system
It carries, while the degree of coupling between call center and operation system can be reduced, in addition, saving message registration by key value database
Data, since the key value database can extend, the capacity of storing data will not be limited, and can reduce the storage of message registration data
Limitation.
It is each step that data processing is realized in the present embodiment below:
Step S10 receives the message registration data that call center generates, and the message registration data is sent to message
Queue;
Data processing system receives the message registration data that call center generates by receiving module first, wherein call
Record data include the information such as number, air time, the duration of call, name of contact person, telephone number, calling record of attending a banquet, and are answered
Work as understanding, which refers to customer name, and telephone number corresponds to the phone of client.Later, the call that will be received
Record data are sent to message queue.
Step S20, from the message queue, it is corresponding by duration to extract the message registration data, and from institute
The message registration data for determining that the duration of call is located within the scope of preset duration in message registration data are stated, it is logical as target
Words record data;
After message queue receives the message registration data of call center's generation, stored in the message queue a plurality of logical
Words record data.In view of in practical experience, there are certain relationship, the duration of call is located at certain for the duration of call and marketing success rate
When within the scope of a duration, marketing success rate is more steady, and after being higher than the range, the increase of the duration of call is not brought accordingly
The growth for success rate of marketing, that is to say, that the client that the duration of call is located within the scope of some duration belongs to potential customers, as a result,
The present embodiment excavates the corresponding message registration data of potential customers based on the duration of call from message queue and (it is logical to be defined as target
Words record data).Specifically, it is compared from the message queue with preset duration range by processing module, when this is default
Long range can be not construed as limiting herein in conjunction with practical experience flexible setting.After comparison, when being located at default for the duration of call
Message registration data in long range then record data as destination call, in this way, what is just stored from the message queue is a plurality of
Destination call record data are defined in message registration data.It is generated it should be noted that message queue receives call center
Message registration data be real-time reception.
Step S30 stores destination call record data into key value database.
After defining destination call record data in a plurality of message registration data stored in message queue, data
Processing system is stored destination call record data into key value database by processing module.Specifically, remember from destination call
Record data extract telephone number as key, and the sequence position of key is then arranged according to the size order of the corresponding duration of call
It sets, the sorting position of the biggish key of the duration of call is forward, and according still further to the sorting position of key, corresponding destination call is recorded
Data are stored into key value database, for example, being stored as data structure shown in following table:
It should be noted that the selection of key and sorting position are not limited to aforesaid way, it can according to actual needs flexibly
Setting.Key value database includes plurality of data structures, and the present embodiment is not limited to above-mentioned when storing destination call record data
The data structure of citing.Further, since it is real-time reception that message queue, which receives the message registration data that call center generates, that
, destination call record data are determined from the message queue in processing module and store destination call record data to key assignments
It is also possible to real-time perfoming in database.
In the present embodiment, after step S30, may include:
Step A, when detecting message registration data inquiry request, extracted from the inquiry request telephone number and
Beginning and ending time to be checked;
That is, data processing system further includes query service module, the query service module be used for message registration data into
Row inquiry.It attends a banquet or related service personnel can trigger inquiry request, query service module at the interface of data processing system
When detecting data inquiry request, telephone number and beginning and ending time to be checked are extracted from the inquiry request, such as
The message registration data in January, 2018 in June, 2018.
Step B is inquired in the key value database using the telephone number and the beginning and ending time as querying condition
Corresponding message registration data and feedback query result.
Later, using the telephone number and rise should only the time as querying condition, the connection is searched in key value database
Talk with the corresponding message registration data for meeting the beginning and ending time, and the message registration data found are passed through into query service mould
Block is fed back, in this way, supporting real time inspection message registration data, improves intelligence.
The message registration data that the data processing method that the present embodiment proposes, first reception call center generate, and will lead to
Words record data are sent to message queue, then from the message queue, extract that the message registration data are corresponding to be passed through
Duration, and determine that destination call records data from message registration data according to the duration of call of extraction, and then by destination call
Record data are stored into key value database.The present embodiment utilizes stream data processing technique, the call generated to call center
Record data are excavated and are stored, more convenient and intelligent, and will not occupy operation system resource, alleviate operation system
Load, while the degree of coupling between call center and operation system is reduced, in addition, saving message registration by key value database
Data, the key value database can extend, and memory capacity will not be limited, and reduce the limitation of message registration data storage.
Further, the second embodiment of data processing method of the present invention is proposed based on first embodiment.Data processing side
The difference of the first embodiment of the second embodiment and data processing method of method is that, referring to Fig. 3, the data processing system is also
Including Push Service module, after the step 30, may include:
Step S40, detect push product time reach when, from the key value database obtain apart from it is current when
Between for the destination call in preset duration record data;
In the present embodiment, which further includes Push Service module, which is used for mesh
Pushes customer recommended products is marked, which refers to product marketing object.By first embodiment it is found that in key value database
The destination call record data of storage are the corresponding message registration data of potential customers, to determine more accurately product marketing pair
As that in the present embodiment, data can be recorded according to destination call and determine target customer from potential customers.
Specifically, it is that timing pushes that data processing system, which can be set to the time that target user pushes recommended products, when
When detecting the time arrival of push product by Push Service module, obtaining apart from current point in time is the mesh in preset duration
Message registration data are marked, optional timing acquisition is apart from the destination call record data that current point in time is within 24 hours.
Step S50 analyzes the destination call record data of acquisition, determines target customer;
Later, the destination call record data of acquisition are analyzed, specifically, records data from the destination call of acquisition
In extract calling record, then calling record is identified, with determine in calling record whether comprising " consulting ", " in advance
Calmly ", " amount of money " etc. is related to the keyword of product purchase intention, and the call comprising being related to product purchase intention keyword is recorded
Corresponding contact person is determined as target customer by sound.
Step S60 obtains the customer information of the target customer from operation system;
In the present embodiment, if client searches in product web, product APP, browses, collected product, Huo Zhe
Site seeks advice from or handled product business under relation line, and operation system just will record the customer information of the client and store,
The customer information includes personal data, access data and asset data.Wherein, personal data include age, gender, region, row
Industry, education degree etc., access data include the frequency for accessing product web or product APP, access time, access away from modern time
The time of site, access away from modern time difference, online lower site consulting or were handled under difference, the product accessed, and visit line
Product etc., asset data includes house property and automobile etc..Data processing system after determining target customer according to target data,
The corresponding customer information of target customer is obtained from operation system.
Step S70 determines the recommended products of the target customer according to the customer information, and pushes away to the target customer
Send the recommended products.
After obtaining the customer information of target customer, by customer information be input in trained neural network model into
Row analysis obtains the feature tag of the target customer of neural network model output, and the feature tag of target customer includes attribute mark
Label, value label, behavior label and demand label, wherein attribute tags are used to describe the personal information of target customer, value mark
The marketing success rate for describing target customer is signed, behavior label is for describing target customer in product web, product APP or phase
The active degree under line in site is closed, demand label is used to describe the preference product of target customer.It should be appreciated that in the present embodiment
In need to train neural network model in advance, the process of training neural network model includes: creation neural network model first, then
Preset sample data is input in the neural network model of creation, and parameter is set, parameter can be set from minimum value
Set, start to train immediately, the result of training output is compared with preset result, obtain training result and default result it
Between difference, and difference be less than preset difference value when the parameter of setting is saved as to trained parameter, be greater than or equal in difference
When preset difference value, parameter is modified, and continues to train, until difference be less than preset difference value, can be obtained and train
Neural network model, or be updated by parameter of the iterative algorithm to the neural network model, and to preset sample
Data are iterated training, by constantly loop iteration, until reaching previously positioned the number of iterations or having restrained
Obtain trained neural network model.
After obtaining the feature tag of target customer, the feature tag of target customer is analyzed, determines target visitor
Characterizing population group belonging to family.Specifically, the difference in data processing system previously according to feature tag is provided with multiple feature people
Group, feature tag possessed by target customer can be compared with the label substance of these preset characterizing population groups, thus
Determine characterizing population group belonging to target customer.For different characterizing population groups, it is corresponding with different recommended products.Further,
The product to match with characterizing population group belonging to target customer is inquired from the product library of operation system, which is determined as mesh
Mark the recommended products of client.Later, by Push Service module, the telephone number based on target customer pushes away the recommended products
It send to the mobile terminal of target customer.
By the above-mentioned means, the present embodiment records data based on the destination call stored in key value database, can position
Target customer out realizes so that the customer information of combining target client is that target customer recommends the product that it most possibly receives
The precision marketing of product.
In addition, the embodiment of the present invention also provides a kind of data processing equipment.
It is the functional block diagram of data processing equipment first embodiment of the present invention referring to Fig. 4, Fig. 4.
In the present embodiment, the data processing equipment includes:
Receiving module 10 is sent out for receiving the message registration data of call center's generation, and by the message registration data
It send to message queue;
Determining module 20, for from the message queue, it is corresponding by duration to extract the message registration data,
And from the message registration data for determining that the duration of call is located within the scope of preset duration in the message registration data, as
Destination call records data;
Memory module 30, for storing destination call record data into key value database.
Wherein, each virtual functions module of above-mentioned data processing equipment is stored in the storage of data processing equipment shown in Fig. 1
It is functional for realizing the institute of data processor in device 1005;When each module is executed by processor 1001, realize to phone
The excavation and storage for the message registration data that center generates, it is more convenient and intelligent, and operation system resource will not be occupied, mitigate
The load of operation system, while the degree of coupling between call center and operation system is reduced, in addition, pass through key value database
Message registration data are saved, which can extend, and the capacity of storing data will not be limited, and reduce message registration number
According to the limitation of storage.
Further, the memory module 30 includes:
Extraction unit, for extracting corresponding telephone number from destination call record data;
The sorting position of the key is arranged as key in setting unit, the telephone number for that will extract;
Storage unit, the sorting position for the key according to setting store corresponding destination call record data to institute
It states in key value database.
Further, the data processing equipment further include:
Extraction module, for extracting connection from the inquiry request when detecting message registration data inquiry request
It is phone and beginning and ending time to be checked;
Feedback module is used for using the telephone number and the beginning and ending time as querying condition, in the key assignments data
Corresponding message registration data and feedback query result are inquired in library.
Further, the data processing equipment further include:
First obtains module, for being obtained from the key value database when detecting that the time of push product reaches
Apart from the destination call record data that current time is in preset duration;
Analysis module determines target customer for analyzing the destination call record data of acquisition;
Second obtains module, for obtaining the customer information of the target customer from operation system;
Pushing module, for determining the recommended products of the target customer according to the customer information, and to the target
Recommended products described in pushes customer.
Further, the analysis module includes:
Calling record extraction unit, for extracting calling record from the destination call of acquisition record data;
Recognition unit, for identifying determine whether the calling record extracted includes to be related to the calling record of extraction
The keyword of product purchase intention;
First determination unit will be corresponding for the calling record for the keyword comprising being related to product purchase intention
Contact person in destination call record data is determined as target customer.
Further, the pushing module includes:
Analytical unit is analyzed for the customer information to be input in trained neural network model, is obtained
The feature tag of the target customer of the neural network model output;
Second determination unit, for determining the recommended products of the target customer according to the feature tag.
Further, second determination unit includes:
It analyzes subelement and determines characterizing population group belonging to the target customer for analyzing the feature tag;
Subelement is inquired, for the inquiry from the product library of operation system and the matched product of the characterizing population group, by institute
State the recommended products that product is determined as the target customer.
Wherein, each in the function realization and above-mentioned data processing method embodiment of modules in above-mentioned data processing equipment
Step is corresponding, and function and realization process no longer repeat one by one here.
In addition, the embodiment of the present invention also provides a kind of computer readable storage medium.
It is stored with data processor on computer readable storage medium of the present invention, wherein the data processor is located
When managing device execution, realize such as the step of above-mentioned data processing method.
Wherein, data processor, which is performed realized method, can refer to each reality of data processing method of the present invention
Example is applied, details are not described herein again.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the system that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or system institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, method of element, article or system.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that terminal device (it can be mobile phone,
Computer, server, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of data processing method, which is characterized in that the data processing method the following steps are included:
The message registration data that call center generates are received, and the message registration data are sent to message queue;
From the message queue, the corresponding duration of call of the message registration data is extracted, and from the message registration number
The message registration data that the duration of call is located within the scope of preset duration are determined in, record data as destination call;
Destination call record data are stored into key value database.
2. data processing method as described in claim 1, which is characterized in that described by destination call record data storage
Step into key value database includes:
Corresponding telephone number is extracted from destination call record data;
Using the telephone number of extraction as key, the sorting position of the key is set;
Corresponding destination call record data are stored into the key value database according to the sorting position of the key of setting.
3. data processing method as described in claim 1, which is characterized in that described by destination call record data storage
To the step in the key value database, comprising:
When detecting message registration data inquiry request, from extracted in the inquiry request telephone number and it is to be checked
The only time;
Using the telephone number and the beginning and ending time as querying condition, corresponding call is inquired in the key value database
Record data, and feedback query result.
4. data processing method as described in claim 1, which is characterized in that described by destination call record data storage
To the step in the key value database, further includes:
When detecting that the time of push product reaches, being obtained from the key value database apart from current time is preset duration
Interior destination call records data;
The destination call record data of acquisition are analyzed, determine target customer;
The customer information of the target customer is obtained from operation system;
The recommended products of the target customer is determined according to the customer information, and is pushed the recommendation to the target customer and produced
Product.
5. data processing method as claimed in claim 4, which is characterized in that described pair acquisition destination call record data into
Row analysis, the step of determining target customer include:
Calling record is extracted from the destination call of acquisition record data;
Identify determine whether the calling record extracted includes to be related to the key of product purchase intention to the calling record of extraction
Word;
For the calling record of the keyword comprising being related to product purchase intention, corresponding destination call is recorded into the connection in data
It is that people is determined as target customer.
6. data processing method as claimed in claim 4, which is characterized in that described to determine the mesh according to the customer information
Mark client recommended products step include:
The customer information is input in trained neural network model and is analyzed, it is defeated to obtain the neural network model
The feature tag of the target customer out;
The recommended products of the target customer is determined according to the feature tag.
7. data processing method as claimed in claim 6, which is characterized in that described to determine the mesh according to the feature tag
Mark client recommended products the step of include:
The feature tag is analyzed, determines characterizing population group belonging to the target customer;
Inquiry and the matched product of the characterizing population group, are determined as the target for the product from the product library of operation system
The recommended products of client.
8. a kind of data processing equipment, which is characterized in that the data processing equipment includes:
Receiving module for receiving the message registration data of call center's generation, and the message registration data is sent to and are disappeared
Cease queue;
Determining module, for from the message queue, it is corresponding by duration to extract the message registration data, and from institute
The message registration data for determining that the duration of call is located within the scope of preset duration in message registration data are stated, it is logical as target
Words record data;
Memory module, for storing destination call record data into key value database.
9. a kind of data processing equipment, which is characterized in that the data processing equipment includes processor, memory and storage
On the memory and the data processor that can be executed by the processor, wherein the data processor is by the place
When managing device and executing, the step of realizing data processing method as described in any one of claims 1 to 7.
10. a kind of computer readable storage medium, which is characterized in that be stored at data on the computer readable storage medium
Program is managed, wherein realizing the number as described in any one of claims 1 to 7 when the data processor is executed by processor
The step of according to processing method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910199189.4A CN110062112A (en) | 2019-03-15 | 2019-03-15 | Data processing method, device, equipment and computer readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910199189.4A CN110062112A (en) | 2019-03-15 | 2019-03-15 | Data processing method, device, equipment and computer readable storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110062112A true CN110062112A (en) | 2019-07-26 |
Family
ID=67316169
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910199189.4A Pending CN110062112A (en) | 2019-03-15 | 2019-03-15 | Data processing method, device, equipment and computer readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110062112A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111475313A (en) * | 2020-03-04 | 2020-07-31 | 江苏理工学院 | Message queue construction method and device suitable for convolutional neural network forward propagation |
CN111745689A (en) * | 2020-07-16 | 2020-10-09 | 浙江百应科技有限公司 | Method for realizing voice robot automatic test through recording playback comparison |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030126180A1 (en) * | 2002-01-03 | 2003-07-03 | Bogart Frank J. | Arrangement for relating contacts to a context |
JP2008021202A (en) * | 2006-07-14 | 2008-01-31 | Csk Holdings Corp | Customer information utilization device |
JP2009218775A (en) * | 2008-03-10 | 2009-09-24 | Oki Electric Ind Co Ltd | Call center system |
-
2019
- 2019-03-15 CN CN201910199189.4A patent/CN110062112A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030126180A1 (en) * | 2002-01-03 | 2003-07-03 | Bogart Frank J. | Arrangement for relating contacts to a context |
JP2008021202A (en) * | 2006-07-14 | 2008-01-31 | Csk Holdings Corp | Customer information utilization device |
JP2009218775A (en) * | 2008-03-10 | 2009-09-24 | Oki Electric Ind Co Ltd | Call center system |
Non-Patent Citations (2)
Title |
---|
刘峪竹,肖侬,刘芳,陈志广,唐黎哲: "基于SSD的Key-Value系统优化设计与实现", 《计算机研究与发展》 * |
赵鑫: "键值数据库在云计算中的应用与实现", 《电子科技大学硕士学位论文》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111475313A (en) * | 2020-03-04 | 2020-07-31 | 江苏理工学院 | Message queue construction method and device suitable for convolutional neural network forward propagation |
CN111745689A (en) * | 2020-07-16 | 2020-10-09 | 浙江百应科技有限公司 | Method for realizing voice robot automatic test through recording playback comparison |
CN111745689B (en) * | 2020-07-16 | 2021-12-21 | 浙江百应科技有限公司 | Method for realizing voice robot automatic test through recording playback comparison |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109767255B (en) | Method for realizing intelligent operation and accurate marketing through big data modeling | |
CN109492772B (en) | Method and device for generating information | |
CN109684330A (en) | User's portrait base construction method, device, computer equipment and storage medium | |
CN111046237B (en) | User behavior data processing method and device, electronic equipment and readable medium | |
CN113157947A (en) | Knowledge graph construction method, tool, device and server | |
US9652740B2 (en) | Fan identity data integration and unification | |
CN103177066A (en) | Analyzing and representing interpersonal relations | |
CN111652468A (en) | Business process generation method and device, storage medium and computer equipment | |
CN111027838A (en) | Crowdsourcing task pushing method, device, equipment and storage medium thereof | |
CN111310032A (en) | Resource recommendation method and device, computer equipment and readable storage medium | |
CN109903122A (en) | House prosperity transaction information processing method, device, equipment and storage medium | |
US10055469B2 (en) | Method and software for retrieving information from big data systems and analyzing the retrieved data | |
CN109190027A (en) | Multi-source recommended method, terminal, server, computer equipment, readable medium | |
CN116881430A (en) | Industrial chain identification method and device, electronic equipment and readable storage medium | |
CN110062112A (en) | Data processing method, device, equipment and computer readable storage medium | |
CN114328947A (en) | Knowledge graph-based question and answer method and device | |
Mohamadina et al. | Business intelligence: concepts, issues and current systems | |
CN110442614B (en) | Metadata searching method and device, electronic equipment and storage medium | |
CN115168603B (en) | Automatic feedback response method, device and storage medium for color ring back tone service process | |
CN115329078A (en) | Text data processing method, device, equipment and storage medium | |
US20220284023A1 (en) | Estimating computational cost for database queries | |
CN113568888A (en) | Index recommendation method and device | |
CN113254796A (en) | Network object label management method and system | |
Mateo | A Knowledge extraction framework for call center analytics | |
US11263192B2 (en) | Hyper-folding information in a uniform interaction feed |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
AD01 | Patent right deemed abandoned | ||
AD01 | Patent right deemed abandoned |
Effective date of abandoning: 20221230 |